This partially reverts commit
fa93b45fd397 ("arm64: Enable vmalloc-huge
with ptdump"), retaining vmalloc-huge support but eliminating the now
redundant mitigation against a race between huge vmap page table freeing
and ptdump, as this issue has now been fixed at core.
We also simultaneously remove the arm64 if-deffery when acquiring the mmap
read lock upon vmap huge page table promotion as it is no longer required.
Note that this patch relies on the preceding vmalloc patch, and should not
be backported alone.
Link: https://lore.kernel.org/20260723-series-vmap-race-fix-v6-5-8cc77dcc0018@kernel.org
Fixes: fa93b45fd397 ("arm64: Enable vmalloc-huge with ptdump")
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: David Hildenbrand (Arm) <david@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Borah, Chaitanya Kumar" <chaitanya.kumar.borah@intel.com>
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Carlier <devnexen@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
#include <linux/ptdump.h>
-DECLARE_STATIC_KEY_FALSE(arm64_ptdump_lock_key);
-
#ifdef CONFIG_PTDUMP
#include <linux/mm_types.h>
#define NO_CONT_MAPPINGS BIT(1)
#define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */
-DEFINE_STATIC_KEY_FALSE(arm64_ptdump_lock_key);
-
u64 kimage_voffset __ro_after_init;
EXPORT_SYMBOL(kimage_voffset);
return 1;
}
-static int __pmd_free_pte_page(pmd_t *pmdp, unsigned long addr,
- bool acquire_mmap_lock)
+int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
{
pte_t *table;
pmd_t pmd;
return 1;
}
- /* See comment in pud_free_pmd_page for static key logic */
table = pte_offset_kernel(pmdp, addr);
pmd_clear(pmdp);
__flush_tlb_kernel_pgtable(addr);
- if (static_branch_unlikely(&arm64_ptdump_lock_key) && acquire_mmap_lock) {
- mmap_read_lock(&init_mm);
- mmap_read_unlock(&init_mm);
- }
-
pte_free_kernel(NULL, table);
return 1;
}
-int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
-{
- /* If ptdump is walking the pagetables, acquire init_mm.mmap_lock */
- return __pmd_free_pte_page(pmdp, addr, /* acquire_mmap_lock = */ true);
-}
-
int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
{
pmd_t *table;
}
table = pmd_offset(pudp, addr);
-
- /*
- * Our objective is to prevent ptdump from reading a PMD table which has
- * been freed. In this race, if pud_free_pmd_page observes the key on
- * (which got flipped by ptdump) then the mmap lock sequence here will,
- * as a result of the mmap write lock/unlock sequence in ptdump, give
- * us the correct synchronization. If not, this means that ptdump has
- * yet not started walking the pagetables - the sequence of barriers
- * issued by __flush_tlb_kernel_pgtable() guarantees that ptdump will
- * observe an empty PUD.
- */
- pud_clear(pudp);
- __flush_tlb_kernel_pgtable(addr);
- if (static_branch_unlikely(&arm64_ptdump_lock_key)) {
- mmap_read_lock(&init_mm);
- mmap_read_unlock(&init_mm);
- }
-
pmdp = table;
next = addr;
end = addr + PUD_SIZE;
do {
if (pmd_present(pmdp_get(pmdp)))
- /*
- * PMD has been isolated, so ptdump won't see it. No
- * need to acquire init_mm.mmap_lock.
- */
- __pmd_free_pte_page(pmdp, next, /* acquire_mmap_lock = */ false);
+ pmd_free_pte_page(pmdp, next);
} while (pmdp++, next += PMD_SIZE, next != end);
+ pud_clear(pudp);
+ __flush_tlb_kernel_pgtable(addr);
pmd_free(NULL, table);
return 1;
}
note_page(pt_st, 0, -1, pte_val(pte_zero));
}
-static void arm64_ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm)
-{
- static_branch_inc(&arm64_ptdump_lock_key);
- ptdump_walk_pgd(st, mm, NULL);
- static_branch_dec(&arm64_ptdump_lock_key);
-}
-
void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
{
unsigned long end = ~0UL;
}
};
- arm64_ptdump_walk_pgd(&st.ptdump, info->mm);
+ ptdump_walk_pgd(&st.ptdump, info->mm, NULL);
}
static void __init ptdump_initialize(void)
}
};
- arm64_ptdump_walk_pgd(&st.ptdump, &init_mm);
+ ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
if (st.wx_pages || st.uxn_pages) {
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
* Concurrent read lock holders are safe: each exclusively owns
* the range it operates on and cannot reach this page table.
*/
-#ifndef CONFIG_ARM64
- scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm)
-#endif
- {
+ scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
if (!pmd_free_pte_page(pmd, addr))
return 0;
return pmd_set_huge(pmd, phys_addr, prot);
return pud_set_huge(pud, phys_addr, prot);
/* See comment in vmap_try_huge_pmd(). */
-#ifndef CONFIG_ARM64
- scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm)
-#endif
- {
+ scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
if (!pud_free_pmd_page(pud, addr))
return 0;
return pud_set_huge(pud, phys_addr, prot);
return p4d_set_huge(p4d, phys_addr, prot);
/* See comment in vmap_try_huge_pmd(). */
-#ifndef CONFIG_ARM64
- scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm)
-#endif
- {
+ scoped_cond_guard(mmap_read_lock_try, return 0, &init_mm) {
if (!p4d_free_pud_page(p4d, addr))
return 0;
return p4d_set_huge(p4d, phys_addr, prot);
projects / thirdparty / kernel / linux.git / commitdiff
